CN101826135A - Be used to strengthen the integrated information fusion of vehicle diagnostics, prediction and maintenance practice - Google Patents
Be used to strengthen the integrated information fusion of vehicle diagnostics, prediction and maintenance practice Download PDFInfo
- Publication number
- CN101826135A CN101826135A CN201010163960A CN201010163960A CN101826135A CN 101826135 A CN101826135 A CN 101826135A CN 201010163960 A CN201010163960 A CN 201010163960A CN 201010163960 A CN201010163960 A CN 201010163960A CN 101826135 A CN101826135 A CN 101826135A
- Authority
- CN
- China
- Prior art keywords
- data
- vehicle
- subsystem
- database
- collecting
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
- G05B19/0428—Safety, monitoring
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24069—Diagnostic
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24216—Supervision of system
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/26—Pc applications
- G05B2219/2637—Vehicle, car, auto, wheelchair
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/008—Registering or indicating the working of vehicles communicating information to a remotely located station
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0841—Registering performance data
- G07C5/085—Registering performance data using electronic data carriers
Abstract
The present invention relates to be used to strengthen the integrated information fusion of vehicle diagnostics, prediction and maintenance practice.Providing a kind of is used to strengthen vehicle diagnostics and prediction algorithm and improves the system and method that vehicle maintenance is put into practice.This method comprises the data of collecting from vehicle component, subsystem and system, and with collected data storage in database.The data of this collection and storage can be come the multiple source of self similarity vehicle or similar components, and can comprise various faults code and operation code and out of Memory, for example physical property of service data that is merged and fault data.This method is to the generation class of different vehicle components, subsystem and system, and the The data data mining technology that is stored in the database is set up feature extractor at each class.This method also generates the sorter of feature being sorted out at each class.This feature extractor and tagsort device are used for determining vehicle component, subsystem or the system situation that when broken down.
Description
Technical field
The present invention relates generally to a kind of system and method that is used to strengthen vehicle diagnostics and prediction algorithm, thereby and especially relates to a kind of by merging the system and method that is used to strengthen vehicle diagnostics and prediction algorithm and vehicle maintenance practice from the information of vehicles of multiple source.
Background technology
The diagnostic monitoring of each Vehicular system is important vehicle design consideration, thereby can the rapid detection system fault, and for the care and maintenance purpose with described fault isolation.These Vehicular systems typically adopt a plurality of subsystems, actuator and sensor, for example Yaw rate sensor, side acceleration sensor, steering direction dish angular transducer etc., and it is used for helping to provide vehicle control.If any sensor, actuator and the subsystem that are associated with these systems break down, then expectation can detect this fault apace and activate failure safe (fail silent or fault are still operated) strategy to prevent that this system is improperly in response to the situation of the mistake that perceives.For the purpose of safeguarding, maintaining and changing, also defective sensor, actuator or subsystem are isolated in expectation.Therefore monitoring each sensor, actuator and the subsystem that use in these systems is necessary with the identification fault.
In Vehicular system, the root that the identification fault takes place and isolate always this fault until component-level or even the subsystem irrespective of size be a kind of design challenge.Each subsystem in Vehicular system and element (as motor vehicle braking system or wheel steering system) be can't help motor vehicle manufacturers design usually, but are provided by external source.Therefore, these elements and subsystem may not understand other subsystem or what element does in whole Vehicular system, and only understands its specific subsystem or how element is operated.Therefore, these external subsystems or element can recognize that they operate improperly, but do not know whether its element or subsystem break down or whether another subsystem or element break down.For example, vehicle can draw in one direction, and it may be braking problem or the result that turns to problem to cause.Yet, because brake system and steering do not know whether another operation is correct, so whole Vehicular system may not be discerned the root of this problem.
Subsystem that each is independent or element can send diagnostic trouble code (DTC), indication problem when its maloperation, but this failure code may not be owing to send the subsystem of this code or the problem of element causes.In other words because subsystem or element operate improperly diagnostic code will be set, but this operation may other subsystem or the element maloperation cause.It is how reliable that expectation knows that the diagnostic code from specific subsystem or element has, thereby determine whether this subsystem or element are the faults of problem.
For employing prevention property measure before taking place in great damage, but the diagnosis of vehicle health status monitoring and the generation of forecasting techniques aid forecasting problem.Can have the system of key hint for the system failure, these technology become more important.In addition, by adopting diagnosis and forecasting techniques, system manufacturer can help prevent its client owing to the fault of each system is discontented with.
Past has been made some effort and developed diagnosis and forecasting techniques to detect and the positioning performance degeneration in each operating system.A kind of existing method based on diagnosis and prediction principle adopts temporal data to excavate.
Summary of the invention
According to instruction of the present invention, a kind of system and method that is used to strengthen vehicle diagnostics and prediction algorithm and the practice of raising vehicle maintenance is disclosed.This method comprises from vehicle component, subsystem and systematic collection data, and with the data storage collected in database.Data collected and storage can be come the multiple source of self similarity vehicle or similar components, and can comprise polytype failure code and operation code and the out of Memory that is merged, for example physical property of service data and fault data.This method generates the class of different vehicle components, subsystem and system, and sets up feature extractor to being stored in the database The data data mining technology at each class.This method also generates sorter, and it is sorted out feature at each class.This feature extractor and tagsort device are used for determining vehicle component, subsystem or the system situation that when broken down.(1), a kind of method that vehicle diagnostics and forecast assessment are provided, described method comprises: collect from a plurality of vehicle component, subsystem and system and the data in a plurality of vehicles source that comprise element, subsystem and the system of different vehicle; With the data storage of collecting in one or more databases; Dissimilar generation classes for collected data; Will be from the data fusion of vehicle component, subsystem and system and the collection of a plurality of vehicles source; And the data that analysis is merged are to be identified in the failure condition in vehicle component, subsystem and the system.(2) according to the method for item (1), are wherein merged the data of collecting from a plurality of data sources and are comprised: set up feature extractor to being stored in the database The data data mining technology at each class; The generating feature sorter, described tagsort device is sorted out feature at each class; And utilize described feature extractor and tagsort device to determine vehicle component, subsystem or the system situation that when broken down.Item (3) according to the method for item (2), further comprises determining when the robustness of the situation of breaking down from the output combination of a plurality of tagsort devices with increase.Item (4) according to the method for item (2), further comprises and utilizes feature extractor and tagsort device to upgrade tagsort device before.Item (5) according to the method for item (1), further comprises and utilizes Fused data to improve the vehicle maintenance process.(6) according to the method for item (1), are wherein collected data and are comprised the data of collecting from the failure condition and the non-failure condition of vehicle component, subsystem and system.Item (7) according to the method for item (1), further comprises and will give remote data center from the data transmission that the vehicle remote information processing is collected.(8) according to the method for item (7), wherein comprise the data storage of collecting in the data storage that will the collect database and one of the database at remote data center place or both on vehicle in database.Item (9) according to the method for item (1), is wherein collected data and is comprised that collection does not comprise the data of failure code.Item (10) according to the method for item (9), is wherein collected the data that the data that do not comprise failure code comprise that collection is relevant with service data with the fault physical property.Item (11), a kind of method that vehicle diagnostics and forecast assessment are provided, described method comprises: the data of collect vehicle component, subsystem and system on vehicle; With the data storage of collecting on vehicle or vehicle outside database; Be transferred to the remote data information processing that to collect from vehicle remote data center; At the remote data center place the dissimilar generation classes of collected data; The data data mining technology in the database that is stored in remote data center is set up feature extractor at each class; At remote data center generating feature sorter, described tagsort device is sorted out feature at each class; Utilize this feature extractor and tagsort device to determine vehicle component, subsystem or the system situation that when broken down; The output combination of a plurality of tagsort devices is determined when the robustness of the situation of breaking down with increase; And the result transmission of failure condition analysis is got back to vehicle.(12) according to the method for item (11), are wherein collected data and are comprised and collecting from a plurality of vehicle component, subsystem and the system of the element, subsystem and the system that comprise different vehicle and the data in a plurality of vehicles source.Item (13) according to the method for item (11), further comprises and utilizes feature extractor and tagsort device to determine when that the situation of breaking down is improved the vehicle maintenance process.(14) according to the method for item (11), are wherein collected data and are comprised the data of collecting from the failure condition and the non-failure condition of vehicle component, subsystem and system.Item (15) according to the method for item (11), further comprises and utilizes feature extractor and tagsort device to upgrade tagsort device before.Item (16) according to the method for item (11), is wherein collected data and is comprised collection and the special rational matter of the fault data relevant with service data.Item (17), a kind of system that vehicle diagnostics and forecast assessment are provided, described system comprises: the device of the data of collect vehicle component, subsystem and system on vehicle; Device with the database of collected data storage on vehicle; With the remote data information processing of collecting be transferred to the device of remote data center; At the device of remote data center at the dissimilar generation classes of collected data; The data data mining technology in the database that is stored in remote data center is set up the device of feature extractor at each class; The device of generating feature sorter, described tagsort device is sorted out feature at each class; Utilize described feature extractor and tagsort device to determine when the broken down device of situation of vehicle component, subsystem or system.(18), according to the system of item (17), the device of wherein collecting data comprises the device of collecting from the data in a plurality of vehicles and a plurality of vehicles source.Item (19) according to the system of item (17), further comprises determining when the device of the robustness of the situation of breaking down from the output combination of a plurality of tagsort devices with increase.Item (20) according to the system of item (17), further comprises and utilizes feature extractor and tagsort device to determine when that the situation that breaks down is to improve the device of vehicle maintenance process.
Further feature of the present invention becomes clearer by ensuing description and the claims that combine with accompanying drawing.
Description of drawings
Fig. 1 is the synoptic diagram of the vehicle of communicating by letter with remote data center;
Fig. 2 illustrates to collect and be used to from the data of the vehicle process flow diagram with the program that strengthens vehicle diagnostics of the present invention and prediction algorithm.
Fig. 3 illustrates the process flow diagram that information fusion is provided and safeguards the program of suggestion;
Fig. 4 illustrates based on the classification of safeguarding Suggestion box shown in Fig. 3 to support the chart of diagnosis;
Fig. 5 process flow diagram that to be vehicle that the service data frame shown in Fig. 3 is shown decompose with 0.3g retarded velocity braking vehicle energy when stopping.
Fig. 6 is that transverse axis represents that the speed longitudinal axis represents the chart of energy, and it illustrates the function that braking energy is the speed of a motor vehicle and weight, and Fig. 6 is the information type that can be provided by the physical property of fault block among Fig. 3.
Embodiment
Thereby about a kind of be exemplary by merging the following description only actually of the embodiment of the invention that information from multiple source strengthens the system and method for vehicle diagnostics and prediction algorithm, and never be intended to limit the present invention or its application or use.
As described in the following, the present invention proposes a kind of system and method that is used to strengthen vehicle diagnostics and prediction algorithm under the situation that does not have additional other sensor or testing circuit, and it also can cause the improvement of vehicle maintenance process.A plurality of diagnosis and prognoses system and element characteristics are merged, thereby strengthen the diagnosis and the performance of prognoses system on vehicle or by long-range loading and deal with data.This process is in conjunction with from the normal of a plurality of vehicles, Vehicular system and element and the information that breaks down.A plurality of features and sorter off-line or define by data mining technology in real time.Then in order to realize that robust diagnosis and prediction are with the sorter combination.The difference of distorted pattern (morphing model) can be used to diagnosis and failure prediction.
The fault development approach of vehicle component or system is made up of a series of degenerate states usually.At a plurality of normal and fault Vehicular system and state acquisition data, and be stored on the vehicle or by remote storage.The form of data can be a measuring-signal, and symbol or signal make it degenerate sensitiveer for specific element or subsystem thereby it is carried out some processing.This signal also can be changed into symbol.This symbol can be the result that the low resolution of signals of vehicles is extracted.Data for those incidents that diagnostic trouble code (DTC) (DTC) is set up and fault are especially sufficient.Out of Memory can be by checking fault physical property and do not provide the data manipulation characteristic of the incident of diagnostic code to obtain.
Basic purpose of the present invention be data mining technology is applied to integrated information and will be integrated on the car from the knowledge that data mining obtains then or the remote diagnosis algorithm in case better identification and isolated fault.The advantage of this method is that it does not require any additional sensor or testing circuit.Be associated with out of Memory by the information that will excavate, for example vehicle trouble code and vehicle maintenance historical information, for example DTC and operation code, this algorithm can provide better vehicle diagnostics algorithm and safeguard that practice is tactful.
Diagnosis and Forecasting Methodology can comprise feature extraction and tagsort.After some system informations (for example signals of vehicles and discrete event) are extracted, this feature by sorter last diagnostic to be provided and to predict the outcome.This Feature Extraction and classification can be on schedule interact with existing mining data and finish or by being finished by sorter of setting up in advance and defining and feature extractor with data.Sorter also can be dynamically updated, and for example by teleprocessing, utilizes the additional data that can use by vehicle use pattern to strengthen diagnosis.Sorter is defined, and it can determine the vehicle-state of degenerating.Sorter (for example support vector machine, Hidden Markov Model (HMM) etc.) with a plurality of classification/states can be generated and hint.Given any data set, the probability relevant with each classification/state will be generated, and it can be used to infer the health status of element and system.
The vehicle health monitoring can use onboard sensor to obtain by reference model or reference data and actual vehicle behavior are compared by means of active monitoring vehicle health status (the subsystem irrespective of size is to vehicle grade).If imminent problem or diagnosis problem are noticed in health monitoring, additional data will be collected the concurrent notice that goes wrong.Required suitable maintenance accessory and breakdown maintenance scheme are transferred to remote device by teleprocessing system or via vehicle-foundation structure.
A plurality of features and a plurality of sorter can be combined to strengthen whole vehicle diagnostics and estimated performance.It also can be used to vehicle diagnostics and prediction on auto model or subsystem irrespective of size, for example determines the element of unusual morning or the element failure rate of system.
Different characteristic provides diagnosis and information of forecasting not at the same level.For example, minimum voltage and alternating-current resistance all provide the information of accumulator health status, but expression different batteries characteristic.Reliable diagnostic will be provided more and predict the outcome in conjunction with a plurality of features.
By utilizing different sorters, feature can provide dissimilar diagnosis and predict the outcome, as scale-of-two formula result, number percent formula result or based on the diagnosis of probability with predict the outcome the different probability of its expression incipient fault.Merge a plurality of sorters and also provide more reliable and more advanced diagnosis and predict the outcome, for example how long sustainable element is.In many application, a plurality of simple relatively Multiple Classifier Fusion are reached better diagnosis better and predict the outcome than attempting to set up single complex classifier together.
To increase reliability, robustness and feasibility for a plurality of features of vehicle diagnostics and prediction and the fusion of a plurality of sorters.This fusion method can be based on all types of blending theories, as theory of probability and decision theory.Have the level of confidence relevant with it based on each feature, single and/or a plurality of sorters are used to the health status of evaluating system.The robustness with enhanced system is merged in the classification of these a plurality of features by utilizing decision block (for example rule-based methodology or any other decision-making system).
Fig. 1 represents to comprise the system 10 of the vehicle 12 with vehicle-mounted module 14,14 operation diagnosis of vehicle-mounted module and prediction algorithm to be monitoring the health status of each vehicle component, subsystem and system, can be stored in the database 16 on the vehicle 12 by the above-mentioned information of vehicle-mounted module 14 collections and data.Vehicle 12 comprises telematics unit 18, and telematics unit 18 wirelessly sends the message that comprises diagnostic trouble code (DTC) etc., and described message can be discerned concrete vehicle problem, is handled and is stored in the database 16 by vehicle-mounted module 14.These message can and merge the remote data center 20 that is stored in the data in the database 22 by analytical information and receive, and it can comprise the information that relates to the identical or relevant issues on similar vehicle.According to next further describing in detail, this remote data center 20 provides data fusion, feature extraction, classification and other data analysis technique to help identification and the problem that provides in the message is provided.
Fig. 2 is expression based on top description by merging from the data of multiple source flow process Figure 30 with the method that strengthens vehicle diagnostics and prediction algorithm.In frame 32, this method is at each and a plurality of vehicle component, subsystem and the data of systematic collection on vehicle 12, and it is monitored in order to diagnose and predict purpose.Collected data can be element, subsystem and system, it can be at fault or non-failure condition, the operation of described like this element, subsystem or system is all analyzed in both cases.Collected data are stored in the database in frame 34, and database can be on vehicle 12 or at remote data center 12.Then, the data of storage are sent to remote data center 20 and are used in frame 36 to generate the class of data or information in frame 34.These classes of data can be any suitable classifications that specific algorithm is programmed analysis.For example, this classification can be an operation element, the element that is about to break down, the current element that breaks down etc.
Next, the class of identification and be sent to frame 38 in frame 36 from the storage data of frame 34, it extracts feature at each class from data.The feature extraction of data (especially in vehicle environmental) is that known procedures and a plurality of known algorithm and mechanism can be used to feature extraction, as support vector machine.Since the data of a class may for another class be not be fit to or desired data, therefore will at each independently class feature extraction is provided.In case the feature of each class is extracted in frame 38, the feature of extracting utilizes the data of storage in frame 34 to be used to generate the sorter (frame 40) of each element, subsystem and system then, and the analysis of data can be used to determine when particular element, subsystem and system exist failure condition like this.Then this classified information is applied to particular element, subsystem and system to determine whether these elements, subsystem and system may exist fault at frame 42.In frame 44, additional data can be added in element, subsystem and the system that is classified, for example fault physical property data and do not have the data manipulation characteristic of diagnostic code incident.In frame 46, load on to the information remote information processing of element, subsystem and system vehicle 12 with the identification fault then, in frame 34, it can be stored in the database 22.
Fig. 3 is flow process Figure 50, and it illustrates the process that is used to merge aforesaid data and improved vehicle maintenance product is provided.In frame 52, based on the data of collecting and other available information, algorithm is through determining whether recognition component, subsystem or Vehicular system exist the process of fault.Particularly, at frame 54, this algorithm is provided at the Feature Fusion between the different characteristic of different elements etc., and is similar in frame 38 and extracts feature at each class that generates.This algorithm utilizes Feature Fusion to detect to determine trend in frame 56, and particularly, whether concrete element, subsystem or system may be in that there is fault constantly in certain in the future, as the result of the trend of following the tracks of based on the known before information about element.Then, in Decision Fusion frame 58, this trend detection information is used to determine whether to take suitable action based on incipient fault.According to the Decision Fusion analysis, in frame 60, algorithm produces specific maintenance suggestion, and it can comprise operation code (LC), for example is about to the braking problem that produces in frame 62.For example, this Decision Fusion and suggestion process can provide vehicle will need engine in certain fate or 95% the degree of confidence of overhauling in certain mileage, or 60% the degree of confidence that provides vehicle will be in certain fate or have problems in certain mileage.Fig. 4 shows the chart that support is diagnosed based on the classification of this suggestion.
The information of using in frame 52 can be provided by any useful source.For example, historical or current service data (for example starting and stop the number of times of incident) can be provided at frame 64.Fig. 5 is flow process Figure 66, and the example of data class is shown, and these data class can be provided and be used by fusion process in frame 52 at frame 64, is illustrated in the decomposition of vehicle with the 0.3g retarded velocity braking vehicle energy when stopping particularly.The kinetic energy rejection of vehicle when flow process Figure 66 is illustrated in the frame 68 and begins to brake with 100% vehicle energy.From then on begin, 75% kinetic energy is consumed in braking and 25% kinetic energy is consumed in other loss in frame 72.For the energy that in frame 70, is consumed in braking, in frame 74 60% be consumed in before braking and in frame 76,15% be consumed in back braking.Before being consumed in frame 74 in the kinetic energy of braking, 55% of this kinetic energy is consumed in rotor and 5% of this kinetic energy is consumed in brake-shoe and sheet in frame 80 in frame 78.Be consumed in frame 76 in the kinetic energy of back braking, 13% of this kinetic energy is consumed in brake drum and 2% of this kinetic energy is consumed in brake-shoe and sheet in frame 84 in frame 82.
Further, the information of fault physical property (for example duty cycle and corrosion) can be provided at frame 90.As an example, Fig. 6 is that transverse axis represents that the speed longitudinal axis represents the chart of energy, and the form of the information that can be provided is shown, and its expression braking energy is as the function of the speed of a motor vehicle and weight.In frame 52, the information that merges to determine diagnosis and prediction from the physical property of service data frame 64 and the fault in frame 90 is the additional information type that can be provided, and it does not comprise the various failure codes in the analog.
The information that is provided in frame 52 comprises various failure codes, and this failure code is represented as the existing time sequencing of identifying and diagnosing failure code (DTCs) in frame 92, and expression and the historical relevant operation code of DTCs in frame 94.
Above discussion only disclosure and description exemplary embodiments of the present invention.Those skilled in the art recognize in not departing from the spirit and scope of the present invention that claim limits easily according to these descriptions and respective drawings and claim can make various changes, distortion and variation.
Claims (10)
1. method that vehicle diagnostics and forecast assessment are provided, described method comprises:
Collect from a plurality of vehicle component, subsystem and system and the data in a plurality of vehicles source that comprise element, subsystem and the system of different vehicle;
With the data storage of collecting in one or more databases;
Dissimilar generation classes for collected data;
Will be from the data fusion of vehicle component, subsystem and system and the collection of a plurality of vehicles source; And
The data that analysis is merged are to be identified in the failure condition in vehicle component, subsystem and the system.
2. according to the process of claim 1 wherein, merge the data of collecting and comprise from a plurality of data sources:
Set up feature extractor to being stored in the database The data data mining technology at each class;
The generating feature sorter, described tagsort device is sorted out feature at each class; And
Utilize described feature extractor and tagsort device to determine vehicle component, subsystem or the system situation that when broken down.
3. according to the method for claim 2, further comprise and to determine when the robustness of the situation of breaking down with increase from the output combination of a plurality of tagsort devices.
4. according to the method for claim 2, further comprise and utilize feature extractor and tagsort device to upgrade tagsort device before.
5. according to the method for claim 1, further comprise and utilize Fused data to improve the vehicle maintenance process.
6. according to the process of claim 1 wherein that collecting data comprises the data of collecting from the failure condition and the non-failure condition of vehicle component, subsystem and system.
7. according to the method for claim 1, further comprise and to give remote data center from the data transmission of vehicle remote information processing collection.
8. according to the method for claim 7, wherein, the data storage of collecting is comprised in database in the data storage that will the collect database and one of the database at remote data center place or both on vehicle.
9. method that vehicle diagnostics and forecast assessment are provided, described method comprises:
The data of vehicle component, subsystem and the system on vehicle of collecting;
With the data storage of collecting on vehicle or vehicle outside database;
Be transferred to the remote data information processing that to collect from vehicle remote data center;
At the remote data center place the dissimilar generation classes of collected data;
The data data mining technology in the database that is stored in remote data center is set up feature extractor at each class;
At remote data center generating feature sorter, described tagsort device is sorted out feature at each class;
Utilize this feature extractor and tagsort device to determine vehicle component, subsystem or the system situation that when broken down;
The output combination of a plurality of tagsort devices is determined when the robustness of the situation of breaking down with increase; And
The result transmission of failure condition analysis is got back to vehicle.
10. system that vehicle diagnostics and forecast assessment are provided, described system comprises:
The device of the data of vehicle component, subsystem and the system on vehicle of collecting;
Device with the database of collected data storage on vehicle;
With the remote data information processing of collecting be transferred to the device of remote data center;
At the device of remote data center at the dissimilar generation classes of collected data;
The data data mining technology in the database that is stored in remote data center is set up the device of feature extractor at each class;
The device of generating feature sorter, described tagsort device is sorted out feature at each class;
Utilize described feature extractor and tagsort device to determine when the broken down device of situation of vehicle component, subsystem or system.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US12/398895 | 2009-03-05 | ||
US12/398,895 US8095261B2 (en) | 2009-03-05 | 2009-03-05 | Aggregated information fusion for enhanced diagnostics, prognostics and maintenance practices of vehicles |
Publications (1)
Publication Number | Publication Date |
---|---|
CN101826135A true CN101826135A (en) | 2010-09-08 |
Family
ID=42678952
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201010163960A Pending CN101826135A (en) | 2009-03-05 | 2010-03-05 | Be used to strengthen the integrated information fusion of vehicle diagnostics, prediction and maintenance practice |
Country Status (3)
Country | Link |
---|---|
US (1) | US8095261B2 (en) |
CN (1) | CN101826135A (en) |
DE (1) | DE102010010043A1 (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103477366A (en) * | 2011-02-21 | 2013-12-25 | 实耐宝公司 | Diagnostic baselining |
CN104691554A (en) * | 2013-12-05 | 2015-06-10 | 现代自动车株式会社 | Inspection system for vehicle and control method thereof |
CN104833532A (en) * | 2014-12-31 | 2015-08-12 | 宁波海泰汽车保养科技有限公司 | 3D four-wheel alignment test method and tester thereof |
CN105005222A (en) * | 2015-06-12 | 2015-10-28 | 山东省科学院自动化研究所 | New-energy electric automobile overall performance improving system and method based on big data |
CN105321228A (en) * | 2014-07-31 | 2016-02-10 | 福特全球技术公司 | Method and apparatus for vehicle data gathering and analysis |
CN106813926A (en) * | 2015-12-01 | 2017-06-09 | 现代自动车株式会社 | For the method for diagnosing faults of vehicle |
WO2018040357A1 (en) * | 2016-08-31 | 2018-03-08 | 深圳市元征科技股份有限公司 | Method for realizing cloud diagnosis of vehicle and related device |
CN108693868A (en) * | 2018-05-25 | 2018-10-23 | 深圳市轱辘车联数据技术有限公司 | The method of failure predication model training, the method and device of vehicle trouble prediction |
WO2019091360A1 (en) * | 2017-11-07 | 2019-05-16 | 比亚迪股份有限公司 | Method and system for acquiring state of vehicle, and comprehensive ground information subsystem |
CN109791679A (en) * | 2016-09-26 | 2019-05-21 | 哈曼国际工业有限公司 | The system and method for prediction for automobile guarantee fraud |
CN111144588A (en) * | 2019-12-27 | 2020-05-12 | 中国科学院电工研究所 | Management system of vehicle PHM system |
CN111753867A (en) * | 2019-03-28 | 2020-10-09 | 通用汽车环球科技运作有限责任公司 | Monitoring and diagnosing vehicle system problems using machine learning classifiers |
CN111767933A (en) * | 2019-05-17 | 2020-10-13 | 北京京东尚科信息技术有限公司 | Method and device for identifying vehicle driving state |
CN113168172A (en) * | 2018-11-30 | 2021-07-23 | 五十铃自动车株式会社 | Model generation device, model generation method, and program |
CN113511150A (en) * | 2020-04-10 | 2021-10-19 | 采埃孚汽车科技(上海)有限公司 | Integrated electronic control unit and vehicle control method |
Families Citing this family (39)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100250061A1 (en) * | 2008-01-15 | 2010-09-30 | Toyota Jidosha Kabushiki Kaisha | Vehicle control device |
DE102008049754A1 (en) * | 2008-09-30 | 2010-04-08 | Continental Automotive Gmbh | Method and device for wear diagnosis of a motor vehicle |
US9329049B2 (en) * | 2009-12-17 | 2016-05-03 | General Motors Llc | Vehicle telematics communications for providing directions to a vehicle service facility |
US8886393B2 (en) * | 2009-12-17 | 2014-11-11 | General Motors Llc | Vehicle telematics communication for providing in-vehicle reminders |
US8312324B2 (en) * | 2010-01-28 | 2012-11-13 | Xerox Corporation | Remote diagnostic system and method based on device data classification |
US8560168B2 (en) | 2010-08-18 | 2013-10-15 | Snap-On Incorporated | System and method for extending communication range and reducing power consumption of vehicle diagnostic equipment |
US8983785B2 (en) | 2010-08-18 | 2015-03-17 | Snap-On Incorporated | System and method for simultaneous display of waveforms generated from input signals received at a data acquisition device |
US9633492B2 (en) | 2010-08-18 | 2017-04-25 | Snap-On Incorporated | System and method for a vehicle scanner to automatically execute a test suite from a storage card |
US8463953B2 (en) | 2010-08-18 | 2013-06-11 | Snap-On Incorporated | System and method for integrating devices for servicing a device-under-service |
CN102529903B (en) * | 2010-12-31 | 2015-10-07 | 上海博泰悦臻电子设备制造有限公司 | Comprehensive vehicle failure detecting system |
US9262873B2 (en) * | 2011-09-23 | 2016-02-16 | Omnitracs, Llc | Systems and methods for processing vehicle data to report performance data interchangeably |
DE102011121441A1 (en) * | 2011-12-16 | 2013-06-20 | GM Global Technology Operations LLC (n. d. Gesetzen des Staates Delaware) | Method for operating a fault diagnosis system of a vehicle and vehicle |
US8732112B2 (en) | 2011-12-19 | 2014-05-20 | GM Global Technology Operations LLC | Method and system for root cause analysis and quality monitoring of system-level faults |
US8924124B2 (en) * | 2012-01-17 | 2014-12-30 | Ford Global Technologies, Llc | Method and system for engine torque control |
US8560165B2 (en) | 2012-01-17 | 2013-10-15 | GM Global Technology Operations LLC | Co-operative on-board and off-board component and system diagnosis and prognosis |
US8849497B2 (en) * | 2012-03-01 | 2014-09-30 | GM Global Technology Operations LLC | Vehicle health prognosis |
EP2709041B1 (en) | 2012-09-17 | 2014-11-12 | Nxp B.V. | Method and System for Monitoring the State of Health of an Electronic Data Carrier |
US8972099B2 (en) * | 2013-02-05 | 2015-03-03 | GM Global Technology Operations LLC | Method and apparatus for on-board/off-board fault detection |
CN103196682B (en) * | 2013-03-21 | 2015-11-18 | 北京交通大学 | Based on the train suspension system fault separating method of the information fusion of D-S evidence theory |
US9324194B2 (en) * | 2013-06-11 | 2016-04-26 | Innova Electronics, Inc. | Method and system for database compilation on a remote electronic device |
US9336244B2 (en) | 2013-08-09 | 2016-05-10 | Snap-On Incorporated | Methods and systems for generating baselines regarding vehicle service request data |
US9430882B2 (en) | 2013-10-11 | 2016-08-30 | Kenton Ho | Computerized vehicle maintenance management system with embedded stochastic modelling |
US20160035152A1 (en) * | 2013-12-31 | 2016-02-04 | Agnik, Llc | Vehicle data mining based on vehicle onboard analysis and cloud-based distributed data stream mining algorithm |
US10699496B2 (en) | 2014-03-05 | 2020-06-30 | Huawei Device Co., Ltd. | Method for processing data on internet of vehicles, server, and terminal |
US9201930B1 (en) | 2014-05-06 | 2015-12-01 | Snap-On Incorporated | Methods and systems for providing an auto-generated repair-hint to a vehicle repair tool |
CN104181839A (en) * | 2014-08-07 | 2014-12-03 | 深圳市元征科技股份有限公司 | Method and device for processing real-time traveling data of vehicles |
US10587639B2 (en) * | 2015-03-10 | 2020-03-10 | Ca, Inc. | Assessing trust of components in systems |
US10984338B2 (en) * | 2015-05-28 | 2021-04-20 | Raytheon Technologies Corporation | Dynamically updated predictive modeling to predict operational outcomes of interest |
US9704141B2 (en) | 2015-11-05 | 2017-07-11 | Snap-On Incorporated | Post-repair data comparison |
CN105426534A (en) * | 2015-12-21 | 2016-03-23 | 华为技术有限公司 | Information determination method and device |
US10692035B2 (en) * | 2016-07-26 | 2020-06-23 | Mitchell Repair Information Company, Llc | Methods and systems for tracking labor efficiency |
US10600261B2 (en) * | 2017-10-05 | 2020-03-24 | GM Global Technology Operations LLC | Vehicle with health-based active self-testing method |
SE1751567A1 (en) | 2017-12-18 | 2019-06-19 | Komatsu Forest Ab | Work machine and method for monitoring a control system at a work machine |
EP3807726B1 (en) * | 2018-06-13 | 2023-06-07 | Cummins, Inc. | Method and system for energy management of hybrid power systems |
DE102019117943A1 (en) * | 2019-07-03 | 2021-01-07 | Bayerische Motoren Werke Aktiengesellschaft | Method, fault management device, computer program and computer program product for fault management for a vehicle |
US11967189B2 (en) | 2020-04-20 | 2024-04-23 | Innova Electronics Corporation | Router for communicating vehicle data to a vehicle resource |
US11651628B2 (en) | 2020-04-20 | 2023-05-16 | Innova Electronics Corporation | Router for vehicle diagnostic system |
DE102020113193B4 (en) | 2020-05-15 | 2023-03-16 | Bayerische Motoren Werke Aktiengesellschaft | Method and system for processing sensor data for transmission to a central unit |
DE102020123721A1 (en) | 2020-09-11 | 2022-03-17 | Volkswagen Aktiengesellschaft | State determination method for a vehicle component, circuit, motor vehicle |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6415395B1 (en) * | 1999-04-02 | 2002-07-02 | General Electric Company | Method and system for processing repair data and fault log data to facilitate diagnostics |
US6609051B2 (en) * | 2001-09-10 | 2003-08-19 | Daimlerchrysler Ag | Method and system for condition monitoring of vehicles |
CN101126929A (en) * | 2007-09-05 | 2008-02-20 | 东北大学 | Continuous miner remote real-time failure forecast and diagnosis method and device |
WO2008140381A1 (en) * | 2007-05-14 | 2008-11-20 | Volvo Technology Corporation | Remote diagnosis modelling |
Family Cites Families (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6738697B2 (en) * | 1995-06-07 | 2004-05-18 | Automotive Technologies International Inc. | Telematics system for vehicle diagnostics |
US6330499B1 (en) * | 1999-07-21 | 2001-12-11 | International Business Machines Corporation | System and method for vehicle diagnostics and health monitoring |
US6795935B1 (en) * | 1999-10-28 | 2004-09-21 | General Electric Company | Diagnosis of faults in a complex system |
US20020007237A1 (en) * | 2000-06-14 | 2002-01-17 | Phung Tam A. | Method and system for the diagnosis of vehicles |
US20020173885A1 (en) * | 2001-03-13 | 2002-11-21 | Lowrey Larkin Hill | Internet-based system for monitoring vehicles |
US6636790B1 (en) * | 2000-07-25 | 2003-10-21 | Reynolds And Reynolds Holdings, Inc. | Wireless diagnostic system and method for monitoring vehicles |
US7092803B2 (en) * | 2000-08-18 | 2006-08-15 | Idsc Holdings, Llc | Remote monitoring, configuring, programming and diagnostic system and method for vehicles and vehicle components |
US6662091B2 (en) * | 2001-06-29 | 2003-12-09 | Battelle Memorial Institute | Diagnostics/prognostics using wireless links |
US6981182B2 (en) * | 2002-05-03 | 2005-12-27 | General Electric Company | Method and system for analyzing fault and quantized operational data for automated diagnostics of locomotives |
US6834256B2 (en) * | 2002-08-30 | 2004-12-21 | General Electric Company | Method and system for determining motor reliability |
US7092937B2 (en) * | 2003-04-07 | 2006-08-15 | General Motors Corporation | Vehicle diagnostic knowledge delivery |
US7715961B1 (en) * | 2004-04-28 | 2010-05-11 | Agnik, Llc | Onboard driver, vehicle and fleet data mining |
US7526461B2 (en) * | 2004-11-17 | 2009-04-28 | Gm Global Technology Operations, Inc. | System and method for temporal data mining |
US7739007B2 (en) * | 2006-03-29 | 2010-06-15 | Snap-On Incorporated | Vehicle diagnostic method and system with intelligent data collection |
US7558771B2 (en) * | 2006-06-07 | 2009-07-07 | Gm Global Technology Operations, Inc. | System and method for selection of prediction tools |
US8103463B2 (en) * | 2006-09-21 | 2012-01-24 | Impact Technologies, Llc | Systems and methods for predicting failure of electronic systems and assessing level of degradation and remaining useful life |
US7509234B2 (en) * | 2007-08-16 | 2009-03-24 | Gm Global Technology Operations, Inc. | Root cause diagnostics using temporal data mining |
JP4453764B2 (en) * | 2008-02-22 | 2010-04-21 | トヨタ自動車株式会社 | Vehicle diagnostic device, vehicle diagnostic system, and diagnostic method |
US9026304B2 (en) * | 2008-04-07 | 2015-05-05 | United Parcel Service Of America, Inc. | Vehicle maintenance systems and methods |
US20090271066A1 (en) * | 2008-04-23 | 2009-10-29 | Underdal Olav M | Diagnostic data mining |
US8374745B2 (en) * | 2008-09-05 | 2013-02-12 | GM Global Technology Operations LLC | Telematics-enabled aggregated vehicle diagnosis and prognosis |
US8676432B2 (en) * | 2010-01-13 | 2014-03-18 | GM Global Technology Operations LLC | Fault prediction framework using temporal data mining |
-
2009
- 2009-03-05 US US12/398,895 patent/US8095261B2/en active Active
-
2010
- 2010-03-03 DE DE102010010043A patent/DE102010010043A1/en not_active Withdrawn
- 2010-03-05 CN CN201010163960A patent/CN101826135A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6415395B1 (en) * | 1999-04-02 | 2002-07-02 | General Electric Company | Method and system for processing repair data and fault log data to facilitate diagnostics |
US6609051B2 (en) * | 2001-09-10 | 2003-08-19 | Daimlerchrysler Ag | Method and system for condition monitoring of vehicles |
WO2008140381A1 (en) * | 2007-05-14 | 2008-11-20 | Volvo Technology Corporation | Remote diagnosis modelling |
CN101126929A (en) * | 2007-09-05 | 2008-02-20 | 东北大学 | Continuous miner remote real-time failure forecast and diagnosis method and device |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11048604B2 (en) | 2011-02-21 | 2021-06-29 | Snap-On Incorporated | Diagnostic baselining |
CN103477366A (en) * | 2011-02-21 | 2013-12-25 | 实耐宝公司 | Diagnostic baselining |
CN104691554A (en) * | 2013-12-05 | 2015-06-10 | 现代自动车株式会社 | Inspection system for vehicle and control method thereof |
CN105321228A (en) * | 2014-07-31 | 2016-02-10 | 福特全球技术公司 | Method and apparatus for vehicle data gathering and analysis |
CN104833532A (en) * | 2014-12-31 | 2015-08-12 | 宁波海泰汽车保养科技有限公司 | 3D four-wheel alignment test method and tester thereof |
CN105005222A (en) * | 2015-06-12 | 2015-10-28 | 山东省科学院自动化研究所 | New-energy electric automobile overall performance improving system and method based on big data |
CN106813926B (en) * | 2015-12-01 | 2019-12-27 | 现代自动车株式会社 | Fault diagnosis method for vehicle |
CN106813926A (en) * | 2015-12-01 | 2017-06-09 | 现代自动车株式会社 | For the method for diagnosing faults of vehicle |
WO2018040357A1 (en) * | 2016-08-31 | 2018-03-08 | 深圳市元征科技股份有限公司 | Method for realizing cloud diagnosis of vehicle and related device |
CN109791679A (en) * | 2016-09-26 | 2019-05-21 | 哈曼国际工业有限公司 | The system and method for prediction for automobile guarantee fraud |
WO2019091360A1 (en) * | 2017-11-07 | 2019-05-16 | 比亚迪股份有限公司 | Method and system for acquiring state of vehicle, and comprehensive ground information subsystem |
CN108693868B (en) * | 2018-05-25 | 2021-06-11 | 深圳市轱辘车联数据技术有限公司 | Method for training fault prediction model, and method and device for predicting vehicle fault |
CN108693868A (en) * | 2018-05-25 | 2018-10-23 | 深圳市轱辘车联数据技术有限公司 | The method of failure predication model training, the method and device of vehicle trouble prediction |
CN113168172A (en) * | 2018-11-30 | 2021-07-23 | 五十铃自动车株式会社 | Model generation device, model generation method, and program |
CN113168172B (en) * | 2018-11-30 | 2024-02-23 | 五十铃自动车株式会社 | Model generation device, model generation method, and program |
CN111753867A (en) * | 2019-03-28 | 2020-10-09 | 通用汽车环球科技运作有限责任公司 | Monitoring and diagnosing vehicle system problems using machine learning classifiers |
CN111767933A (en) * | 2019-05-17 | 2020-10-13 | 北京京东尚科信息技术有限公司 | Method and device for identifying vehicle driving state |
CN111144588A (en) * | 2019-12-27 | 2020-05-12 | 中国科学院电工研究所 | Management system of vehicle PHM system |
CN113511150A (en) * | 2020-04-10 | 2021-10-19 | 采埃孚汽车科技(上海)有限公司 | Integrated electronic control unit and vehicle control method |
Also Published As
Publication number | Publication date |
---|---|
US20100228423A1 (en) | 2010-09-09 |
DE102010010043A1 (en) | 2010-11-25 |
US8095261B2 (en) | 2012-01-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101826135A (en) | Be used to strengthen the integrated information fusion of vehicle diagnostics, prediction and maintenance practice | |
US9721399B2 (en) | Vehicle diagnosing apparatus, vehicle diagnosing system, and diagnosing method | |
CN102069781B (en) | Allow vehicle diagnostics and the forecast of telematic polymerization | |
CN103493019B (en) | Many Agents cooperation vehicle breakdown diagnostic system and the method being associated | |
CN107271839B (en) | Method and control device for monitoring an on-board electrical system of a vehicle | |
CN102375452B (en) | Event-driven data mining method for improving fault code settings and isolating faults | |
EP2803048B1 (en) | System and method for providing diagnostic fault information | |
CN102200487A (en) | Event-driven fault diagnosis framework for automotive systems | |
CN103048992A (en) | Method and system for remote monitoring and cloud diagnosis of automobile faults | |
US20090306849A1 (en) | System for diagnosis of motor vehicles, and for reception of vehicles at a repair facility | |
CN114585983A (en) | Method, device and system for detecting abnormal operation state of equipment | |
WO2012047529A1 (en) | Adaptive remote maintenance of rolling stocks | |
CN105159283A (en) | Remote fault analysis and feedback system of urban rail transit vehicle | |
KR20170076131A (en) | Monitoring System And Method Of Driving Data For Vehicle Breakdown Diagnostics And Analysis | |
US20160148447A1 (en) | Method, system and computer-readable recording medium for managing abnormal state of vehicle | |
CN112606779B (en) | Automobile fault early warning method and electronic equipment | |
KR102255599B1 (en) | System and method for providing vehicle diagnosis service | |
US20220284740A1 (en) | Method for determining the operating state of vehicle components | |
WO2021111728A1 (en) | Failure symptom detection device, failure symptom detection system, failure symptom detection method, and failure symptom detection program | |
Goyal et al. | Smart vehicle: Online prognosis for vehicle health monitoring | |
WO2021111726A1 (en) | Fault diagnosis device, fault diagnosis system, fault diagnosis method, and fault diagnosis program | |
JP2004306880A (en) | Moving body abnormality detection system, moving body, and ground system | |
JP7468778B2 (en) | Vehicle abnormality detection device and vehicle abnormality detection method | |
US20190371092A1 (en) | Method and Control Unit for Storing Error Information of a Vehicle in at Least One Vehicle Component of the Vehicle, Vehicle Component Unit Having a Memory Device, and Method for Producing a Vehicle Component Unit | |
JP7367773B2 (en) | Fault diagnosis device, fault diagnosis system, fault diagnosis method, and fault diagnosis program |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20100908 |
|
WD01 | Invention patent application deemed withdrawn after publication |